Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A wearable apparatus comprising: a frame having a memory and processor associated therewith; an infrared camera associated with the frame and in communication with the processor, the infrared camera configured to track an eye of a wearer; at least one microphone associated with the frame, the at least one microphone configured to receive a directional instruction from the processor, the directional instruction based upon, at least in part, an adaptive beamforming analysis performed in response to a detected eye movement from the infrared camera, wherein an identification of a non-wearer of the apparatus is performed based upon detecting a pre-defined eye movement of the wearer, wherein detecting the pre-defined eye movement of the wearer triggers a setting that avoids inadvertently resetting the directional instruction if the wearer looks away from the non-wearer, wherein the at least one microphone includes a beamformer with a spatial postfilter and a model based reverberation equalizer configured to suppress reverberation at the spatial postfilter; and a speaker associated with the frame, the speaker configured to provide an audio signal received at the at least one microphone to the wearer only.
A wearable device enhances communication by using a frame containing a processor and memory, along with an infrared camera that tracks the wearer's eye movements. Based on eye movement, the processor performs adaptive beamforming analysis to determine the direction of interest. At least one microphone on the frame receives directional instructions from the processor based on this analysis. The system identifies a person the wearer is looking at using a predefined eye movement and prevents the microphone direction from resetting when the wearer looks away from that person. The microphone employs a beamformer with spatial postfiltering and reverberation equalization to suppress unwanted echoes. Audio received by the microphone is then played to the wearer through a speaker on the frame.
2. The wearable apparatus of claim 1 , wherein the processor is configured to convert the audio signal to text.
This wearable device described in the previous claim also includes a processor that converts the received audio signal into text.
3. The wearable apparatus of claim 2 , further comprising: at least one lens configured to receive the text from the processor and to provide the text to the wearer.
Building upon the audio-to-text functionality, this device includes lenses that receive the converted text from the processor and display it to the wearer. The wearable apparatus has a frame having a memory and processor associated therewith; an infrared camera associated with the frame and in communication with the processor, the infrared camera configured to track an eye of a wearer; at least one microphone associated with the frame, the at least one microphone configured to receive a directional instruction from the processor, the directional instruction based upon, at least in part, an adaptive beamforming analysis performed in response to a detected eye movement from the infrared camera, wherein an identification of a non-wearer of the apparatus is performed based upon detecting a pre-defined eye movement of the wearer, wherein detecting the pre-defined eye movement of the wearer triggers a setting that avoids inadvertently resetting the directional instruction if the wearer looks away from the non-wearer, wherein the at least one microphone includes a beamformer with a spatial postfilter and a model based reverberation equalizer configured to suppress reverberation at the spatial postfilter; and a speaker associated with the frame, the speaker configured to provide an audio signal received at the at least one microphone to the wearer only.
4. The wearable apparatus of claim 2 wherein the memory is configured to store at least one of contact information and conversation log files based upon the converted text.
This device with audio-to-text capabilities also stores contact information and conversation logs based on the converted text in its memory. The wearable apparatus has a frame having a memory and processor associated therewith; an infrared camera associated with the frame and in communication with the processor, the infrared camera configured to track an eye of a wearer; at least one microphone associated with the frame, the at least one microphone configured to receive a directional instruction from the processor, the directional instruction based upon, at least in part, an adaptive beamforming analysis performed in response to a detected eye movement from the infrared camera, wherein an identification of a non-wearer of the apparatus is performed based upon detecting a pre-defined eye movement of the wearer, wherein detecting the pre-defined eye movement of the wearer triggers a setting that avoids inadvertently resetting the directional instruction if the wearer looks away from the non-wearer, wherein the at least one microphone includes a beamformer with a spatial postfilter and a model based reverberation equalizer configured to suppress reverberation at the spatial postfilter; and a speaker associated with the frame, the speaker configured to provide an audio signal received at the at least one microphone to the wearer only.
5. The wearable apparatus of claim 1 , further comprising: a facial recognition camera associated with the frame, the facial recognition camera configured to identify the non-wearer of the apparatus.
The wearable device, that enhances communication by using a frame containing a processor and memory, along with an infrared camera that tracks the wearer's eye movements to steer microphones, incorporates a facial recognition camera. This camera identifies the person the wearer is focusing on, enhancing the device's ability to filter and amplify their speech.
6. The wearable apparatus of claim 1 , wherein the speaker is included within at least one headphone in communication with the processor.
In the wearable communication device, the speaker which plays audio to the wearer is integrated within a headphone connected to the processor. The wearable apparatus has a frame having a memory and processor associated therewith; an infrared camera associated with the frame and in communication with the processor, the infrared camera configured to track an eye of a wearer; at least one microphone associated with the frame, the at least one microphone configured to receive a directional instruction from the processor, the directional instruction based upon, at least in part, an adaptive beamforming analysis performed in response to a detected eye movement from the infrared camera, wherein an identification of a non-wearer of the apparatus is performed based upon detecting a pre-defined eye movement of the wearer, wherein detecting the pre-defined eye movement of the wearer triggers a setting that avoids inadvertently resetting the directional instruction if the wearer looks away from the non-wearer, wherein the at least one microphone includes a beamformer with a spatial postfilter and a model based reverberation equalizer configured to suppress reverberation at the spatial postfilter; and a speaker associated with the frame, the speaker configured to provide an audio signal received at the at least one microphone to the wearer only.
7. The wearable apparatus of claim 1 , wherein the directional instruction is based upon, at least in part, an identification of the non-wearer of the apparatus.
The wearable device, that enhances communication by using a frame containing a processor and memory, along with an infrared camera that tracks the wearer's eye movements to steer microphones, bases the microphone direction on identifying the person the wearer is looking at. Adaptive beamforming uses this identified person to improve audio capture.
8. The wearable apparatus of claim 1 , further comprising: at least one lens configured to display visual feedback to the wearer, the visual feedback including at least one of beam shape, beam direction, and the identified non-wearer of the apparatus.
The wearable device includes lenses that provide visual feedback to the wearer, including the shape and direction of the audio beam and the identity of the person being focused on. The wearable apparatus has a frame having a memory and processor associated therewith; an infrared camera associated with the frame and in communication with the processor, the infrared camera configured to track an eye of a wearer; at least one microphone associated with the frame, the at least one microphone configured to receive a directional instruction from the processor, the directional instruction based upon, at least in part, an adaptive beamforming analysis performed in response to a detected eye movement from the infrared camera, wherein an identification of a non-wearer of the apparatus is performed based upon detecting a pre-defined eye movement of the wearer, wherein detecting the pre-defined eye movement of the wearer triggers a setting that avoids inadvertently resetting the directional instruction if the wearer looks away from the non-wearer, wherein the at least one microphone includes a beamformer with a spatial postfilter and a model based reverberation equalizer configured to suppress reverberation at the spatial postfilter; and a speaker associated with the frame, the speaker configured to provide an audio signal received at the at least one microphone to the wearer only.
9. A method comprising: tracking an eye of a wearer using a camera associated with a frame, the frame having a processor and a memory associated therewith; receiving a directional instruction from the processor at a microphone associated with the frame, the directional instruction based upon, at least in part, an adaptive beamforming analysis performed in response to a detected eye movement from the camera, wherein an identification of a non-wearer of the apparatus is performed based upon detecting a pre-defined eye movement of the wearer, wherein detecting the pre-defined eye movement of the wearer triggers a setting that avoids inadvertently resetting the directional instruction if the wearer looks away from the non-wearer, wherein the at least one microphone includes a beamformer with a spatial postfilter and a model based reverberation equalizer configured to suppress reverberation at the spatial postfilter; adjusting a direction of the at least one microphone, based upon the directional instruction; receiving an audio signal at the at least one microphone; and providing the audio signal to the wearer only using a speaker associated with the frame.
A wearable device enhances communication by tracking the wearer's eye movements using a camera and processor on a frame. The processor performs adaptive beamforming analysis to determine a direction of interest, based on eye movement. At least one microphone on the frame receives directional instructions from the processor. The system identifies a person the wearer is looking at using a predefined eye movement and prevents the microphone direction from resetting when the wearer looks away from that person. The microphone employs a beamformer with spatial postfiltering and reverberation equalization to suppress unwanted echoes. Audio received by the microphone is then played to the wearer through a speaker on the frame.
10. The method of claim 9 , further comprising: converting, using the processor, the audio signal to text.
This communication method includes the step of converting the received audio signal into text using the processor. Tracking an eye of a wearer using a camera associated with a frame, the frame having a processor and a memory associated therewith; receiving a directional instruction from the processor at a microphone associated with the frame, the directional instruction based upon, at least in part, an adaptive beamforming analysis performed in response to a detected eye movement from the camera, wherein an identification of a non-wearer of the apparatus is performed based upon detecting a pre-defined eye movement of the wearer, wherein detecting the pre-defined eye movement of the wearer triggers a setting that avoids inadvertently resetting the directional instruction if the wearer looks away from the non-wearer, wherein the at least one microphone includes a beamformer with a spatial postfilter and a model based reverberation equalizer configured to suppress reverberation at the spatial postfilter; adjusting a direction of the at least one microphone, based upon the directional instruction; receiving an audio signal at the at least one microphone; and providing the audio signal to the wearer only using a speaker associated with the frame.
11. The method of claim 10 , further comprising: receiving the text from the processor and providing the text to at least one lens.
This method also includes the step of displaying the converted text from the processor on lenses visible to the wearer. Tracking an eye of a wearer using a camera associated with a frame, the frame having a processor and a memory associated therewith; receiving a directional instruction from the processor at a microphone associated with the frame, the directional instruction based upon, at least in part, an adaptive beamforming analysis performed in response to a detected eye movement from the camera, wherein an identification of a non-wearer of the apparatus is performed based upon detecting a pre-defined eye movement of the wearer, wherein detecting the pre-defined eye movement of the wearer triggers a setting that avoids inadvertently resetting the directional instruction if the wearer looks away from the non-wearer, wherein the at least one microphone includes a beamformer with a spatial postfilter and a model based reverberation equalizer configured to suppress reverberation at the spatial postfilter; adjusting a direction of the at least one microphone, based upon the directional instruction; receiving an audio signal at the at least one microphone; and providing the audio signal to the wearer only using a speaker associated with the frame; converting, using the processor, the audio signal to text.
12. The method of claim 10 , further comprising: storing at least one of contact information and conversation log files based upon the converted text in the memory.
The described method includes the step of storing contact information and conversation logs based on the converted text in the device's memory. Tracking an eye of a wearer using a camera associated with a frame, the frame having a processor and a memory associated therewith; receiving a directional instruction from the processor at a microphone associated with the frame, the directional instruction based upon, at least in part, an adaptive beamforming analysis performed in response to a detected eye movement from the camera, wherein an identification of a non-wearer of the apparatus is performed based upon detecting a pre-defined eye movement of the wearer, wherein detecting the pre-defined eye movement of the wearer triggers a setting that avoids inadvertently resetting the directional instruction if the wearer looks away from the non-wearer, wherein the at least one microphone includes a beamformer with a spatial postfilter and a model based reverberation equalizer configured to suppress reverberation at the spatial postfilter; adjusting a direction of the at least one microphone, based upon the directional instruction; receiving an audio signal at the at least one microphone; and providing the audio signal to the wearer only using a speaker associated with the frame; converting, using the processor, the audio signal to text.
13. The method of claim 9 , further comprising: identifying the non-wearer of the apparatus using a facial recognition camera associated with the frame.
This wearable communication enhancement method includes identifying the person the wearer is looking at using a facial recognition camera on the frame. Tracking an eye of a wearer using a camera associated with a frame, the frame having a processor and a memory associated therewith; receiving a directional instruction from the processor at a microphone associated with the frame, the directional instruction based upon, at least in part, an adaptive beamforming analysis performed in response to a detected eye movement from the camera, wherein an identification of a non-wearer of the apparatus is performed based upon detecting a pre-defined eye movement of the wearer, wherein detecting the pre-defined eye movement of the wearer triggers a setting that avoids inadvertently resetting the directional instruction if the wearer looks away from the non-wearer, wherein the at least one microphone includes a beamformer with a spatial postfilter and a model based reverberation equalizer configured to suppress reverberation at the spatial postfilter; adjusting a direction of the at least one microphone, based upon the directional instruction; receiving an audio signal at the at least one microphone; and providing the audio signal to the wearer only using a speaker associated with the frame.
14. The method of claim 9 , wherein the speaker is included within at least one headphone in communication with the processor.
In the wearable communication enhancement method, the audio is played to the wearer through a speaker integrated within a headphone connected to the processor. Tracking an eye of a wearer using a camera associated with a frame, the frame having a processor and a memory associated therewith; receiving a directional instruction from the processor at a microphone associated with the frame, the directional instruction based upon, at least in part, an adaptive beamforming analysis performed in response to a detected eye movement from the camera, wherein an identification of a non-wearer of the apparatus is performed based upon detecting a pre-defined eye movement of the wearer, wherein detecting the pre-defined eye movement of the wearer triggers a setting that avoids inadvertently resetting the directional instruction if the wearer looks away from the non-wearer, wherein the at least one microphone includes a beamformer with a spatial postfilter and a model based reverberation equalizer configured to suppress reverberation at the spatial postfilter; adjusting a direction of the at least one microphone, based upon the directional instruction; receiving an audio signal at the at least one microphone; and providing the audio signal to the wearer only using a speaker associated with the frame.
15. The method of claim 9 , wherein the directional instruction is based upon, at least in part, the identification of a non-wearer of the apparatus.
The wearable communication enhancement method bases the microphone's directional instruction partly on the identified person the wearer is looking at. Tracking an eye of a wearer using a camera associated with a frame, the frame having a processor and a memory associated therewith; receiving a directional instruction from the processor at a microphone associated with the frame, the directional instruction based upon, at least in part, an adaptive beamforming analysis performed in response to a detected eye movement from the camera, wherein an identification of a non-wearer of the apparatus is performed based upon detecting a pre-defined eye movement of the wearer, wherein detecting the pre-defined eye movement of the wearer triggers a setting that avoids inadvertently resetting the directional instruction if the wearer looks away from the non-wearer, wherein the at least one microphone includes a beamformer with a spatial postfilter and a model based reverberation equalizer configured to suppress reverberation at the spatial postfilter; adjusting a direction of the at least one microphone, based upon the directional instruction; receiving an audio signal at the at least one microphone; and providing the audio signal to the wearer only using a speaker associated with the frame.
16. The method of claim 9 , further comprising: displaying visual feedback to the wearer on at least one lens, the visual feedback including at least one of beam shape, beam direction, and the identified non-wearer of the apparatus.
The method provides visual feedback to the wearer on lenses, showing the audio beam's shape and direction and the identified person. Tracking an eye of a wearer using a camera associated with a frame, the frame having a processor and a memory associated therewith; receiving a directional instruction from the processor at a microphone associated with the frame, the directional instruction based upon, at least in part, an adaptive beamforming analysis performed in response to a detected eye movement from the camera, wherein an identification of a non-wearer of the apparatus is performed based upon detecting a pre-defined eye movement of the wearer, wherein detecting the pre-defined eye movement of the wearer triggers a setting that avoids inadvertently resetting the directional instruction if the wearer looks away from the non-wearer, wherein the at least one microphone includes a beamformer with a spatial postfilter and a model based reverberation equalizer configured to suppress reverberation at the spatial postfilter; adjusting a direction of the at least one microphone, based upon the directional instruction; receiving an audio signal at the at least one microphone; and providing the audio signal to the wearer only using a speaker associated with the frame.
17. A wearable apparatus comprising: a frame having a memory and processor associated therewith; an infrared camera associated with the frame and in communication with the processor, the infrared camera configured to track an eye of a wearer, wherein an identification of a target of the apparatus is performed based upon detecting a pre-defined eye movement of the wearer; a second camera associated with the frame and in communication with the processor, the second camera configured to track a position of the target of the apparatus upon detecting the pre-defined eye movement of the wearer; at least one microphone associated with the frame, the at least one microphone configured to receive a directional instruction from the processor based upon adaptive beamforming analysis performed by the processor and the position of the target of the apparatus, wherein the at least one microphone includes a beamformer with a spatial postfilter and a model based reverberation equalizer configured to suppress reverberation at the spatial postfilter; and a speaker associated with the frame, the speaker configured to provide an audio signal received at the at least one microphone to the wearer only.
A wearable device enhances communication using a frame with a processor and memory. An infrared camera tracks the wearer's eye; a predefined eye movement identifies a target. A second camera tracks the target's position after the eye movement is detected. Microphones receive directional instructions from the processor based on adaptive beamforming and the target's position. The microphones use beamforming, spatial postfiltering, and reverberation equalization. Audio from the microphones is played to the wearer only through a speaker on the frame.
Unknown
December 19, 2017
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.